Release 0.5 (#1001)

* Prepare for 0.5 release

Signed-off-by: Sachidanand Alle <[email protected]>

* temp decrease for code cov threshold

Signed-off-by: Sachidanand Alle <[email protected]>

* fix target url

Signed-off-by: Sachidanand Alle <[email protected]>

* add deprecation for tta

Signed-off-by: Sachidanand Alle <[email protected]>

* add links

Signed-off-by: Sachidanand Alle <[email protected]>

* fix pathology training

Signed-off-by: Sachidanand Alle <[email protected]>

* fix readme

Signed-off-by: Sachidanand Alle <[email protected]>

Signed-off-by: Sachidanand Alle <[email protected]>

Author: SachidanandAlle

.github/codecov.yml

@@ -13,7 +13,7 @@ coverage:
   status:
     project:
       default:
-        target: 60%
+        target: 45%
         threshold: 10
         base: parent
         if_no_uploads: error

Dockerfile

@@ -14,7 +14,7 @@
 # to use different version of MONAI pass `--build-arg MONAI_IMAGE=...`
 # to exclude ORTHANC pass `--build-arg ORTHANC=false`
 
-ARG MONAI_IMAGE=projectmonai/monai:1.0.0rc3
+ARG MONAI_IMAGE=projectmonai/monai:1.0.0
 ARG ORTHANC=false
 ARG BUILD_OHIF=true
 

README.md

@@ -37,14 +37,12 @@ with [MONAI](https://github.com/Project-MONAI). Refer to full [MONAI Label docum
 
 ## Sample Apps in MONAILabel
 
-![DEMO](https://raw.githubusercontent.com/Project-MONAI/MONAILabel/main/docs/images/sampleApps_index.jpeg)
+![image](https://raw.githubusercontent.com/Project-MONAI/MONAILabel/main/docs/images/sampleApps_index.jpeg)
 
-Demo on labeling tasks with visualization tools 3D Slicer, OHIF, and QuPath
+[MONAI Label](https://youtu.be/m2rYorVwXk4) | [Demo Videos](https://www.youtube.com/c/ProjectMONAI)
 
-[MONAI Label](https://youtu.be/m2rYorVwXk4) | [Demo](https://youtu.be/o8HipCgSZIw?t=1319)
-
-
-![DEMO](https://raw.githubusercontent.com/Project-MONAI/MONAILabel/main/docs/images/demo.png)
+MONAI Label with visualization tools 3D Slicer, OHIF, DSA, QuPath, CVAT etc..
+![image](https://raw.githubusercontent.com/Project-MONAI/MONAILabel/main/docs/images/demo.png)
 <table>
 <tr>
 <td><img src="https://raw.githubusercontent.com/Project-MONAI/MONAILabel/main/docs/images/ohif.png" alt="drawing" width="150"/></td>
@@ -58,6 +56,19 @@ Demo on labeling tasks with visualization tools 3D Slicer, OHIF, and QuPath
 
 > _The codebase is currently under active development._
 
+- Framework for developing and deploying MONAI Label Apps to train and infer AI models
+- Compositional & portable APIs for ease of integration in existing workflows
+- Customizable labeling app design for varying user expertise
+- Annotation support via [3DSlicer](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/slicer)
+  & [OHIF](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/ohif) for radiology
+- Annotation support via [QuPath](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/qupath)
+  , [Digital Slide Archive](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/dsa)
+  & [CVAT](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/cvat) for
+  pathology
+- Annotation support via [CVAT](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/cvat) for Endoscopy
+- PACS connectivity via [DICOMWeb](https://www.dicomstandard.org/using/dicomweb)
+- Automated Active Learning workflow for endoscopy using [CVAT](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/cvat)
+
 **Radiology App**
    This app has example models to do both interactive and automated segmentation over radiology (3D)
    images. Including auto segmentation with the latest deep learning models (e.g., UNet, UNETR) for multiple abdominal
@@ -73,28 +84,16 @@ Demo on labeling tasks with visualization tools 3D Slicer, OHIF, and QuPath
    anatomies. The specification for MONAILabel integration of the Bundle app links archived Model-Zoo for customized labeling
    (e.g., the third-party transformer model for labeling renal cortex, medulla, and pelvicalyceal system. Interactive tools such as DeepEdits).
 
-- Framework for developing and deploying MONAI Label Apps to train and infer AI models
-- Compositional & portable APIs for ease of integration in existing workflows
-- Customizable labeling app design for varying user expertise
-- Annotation support via [3DSlicer](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/slicer)
-  & [OHIF](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/ohif) for radiology
-- Annotation support via [QuPath](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/qupath)
-  , [Digital Slide Archive](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/dsa)
-  & [CVAT](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/cvat) for
-  pathology
-- Annotation support via [CVAT](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/cvat) for Endoscopy
-- PACS connectivity via [DICOMWeb](https://www.dicomstandard.org/using/dicomweb)
+**Endoscopy App**
+   The Bundle app enables users to use interactive, automated segmentation and classification models over 2D images for endoscopy usecase.
+   Combined with CVAT, it will demonstrate the fully automated Active Learning workflow to train + fine-tune a model.
 
 ## Installation
 
 Start using MONAI Label with just three steps:
-
-![DEMO](https://raw.githubusercontent.com/Project-MONAI/MONAILabel/main/docs/images/install_steps.jpeg)
-
-
+![image](https://raw.githubusercontent.com/Project-MONAI/MONAILabel/main/docs/images/install_steps.jpeg)
 
 MONAI Label supports following OS with **GPU/CUDA** enabled.
-
 - Ubuntu: Please see the [installation guide](https://docs.monai.io/projects/label/en/latest/installation.html).
 - [Windows](https://docs.monai.io/projects/label/en/latest/installation.html#windows)
 
@@ -116,6 +115,7 @@ git clone https://github.com/Project-MONAI/MONAILabel
 pip install -r MONAILabel/requirements.txt
 export PATH=$PATH:`pwd`/MONAILabel/monailabel/scripts
 ```
+If you are using DICOM-Web + OHIF then you have to build OHIF package separate.  Please refer [here](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/ohif#development-setup).
 
 #### [Weekly Release](https://pypi.org/project/monailabel-weekly/)
 
@@ -174,7 +174,6 @@ algorithms, develpoment and integration.
 MONAI Label is most currently tested and supported with stable release of 3D Slicer every version. Preview version of 3D Slicer is not fully tested and supported.
 
 To install stable released version of 3D Slicer, see [3D Slicer installation](https://download.slicer.org/).
-
 Currently, Windows and Linux version are supported.
 
 ### OHIF (Web-based)
@@ -183,19 +182,24 @@ The Open Health Imaging Foundation (OHIF) Viewer is an open source, web-based, m
 It aims to provide a core framework for building complex imaging applications.
 
 At this point OHIF can be used to annotate the data in the DICOM server via the MONAI Label server.
-
 To use OHIF web-based application, refer to [extensible web imaging platform](https://ohif.org/)
 
 ### QuPath
 
-Quantitative Pathology & Bioimage Analysis (QuPath)
-
-QuPath is an open, powerful, flexible, extensible software platform for bioimage analysis.
+Quantitative Pathology & Bioimage Analysis (QuPath) is an open, powerful, flexible, extensible software platform for bioimage analysis.
 
 To install stable released version of QuPath, see [QuPath installation](https://qupath.github.io/).
-
 Currently, Windows and Linux version are supported. Detailed documentation can be found [QuPath Doc](https://qupath.readthedocs.io/en/stable/).
 
+
+### CVAT
+
+CVAT is an interactive video and image annotation tool for computer vision.
+
+To install stable released version of CVAT, see [CVAT installation](https://github.com/opencv/cvat).
+Currently, Windows and Linux version are supported. Detailed documentation can be found [CVAT Doc](https://opencv.github.io/cvat/docs/).
+
+
 ## Plugins
 
 ### [3D Slicer](https://download.slicer.org/) (radiology)
@@ -258,9 +262,14 @@ Install [CVAT](https://openvinotoolkit.github.io/cvat/docs/getting_started) and
 enable [Semi-Automatic and Automatic Annotation](https://openvinotoolkit.github.io/cvat/docs/administration/advanced/installation_automatic_annotation/)
 .
 Refer [CVAT Instructions](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/cvat) for deploying available MONAILabel
-pathology models into CVAT.
+pathology/endoscopy models into CVAT.
 
-![image](https://raw.githubusercontent.com/Project-MONAI/MONAILabel/main/docs/images/cvat_detector.jpeg)
+<table>
+<tr>
+<td><img src="https://raw.githubusercontent.com/Project-MONAI/MONAILabel/main/docs/images/cvat_detector.jpeg" width="300"/></td>
+<td><img src="https://raw.githubusercontent.com/Project-MONAI/MONAILabel/main/docs/images/cvat_active_learning.jpeg" width="300"/></td>
+</tr>
+</table>
 
 ## Cite
 
@@ -319,3 +328,5 @@ on [MONAI Label's GitHub Discussions tab](https://github.com/Project-MONAI/MONAI
 - PyPI package: https://pypi.org/project/monailabel/
 - Weekly previews: https://pypi.org/project/monailabel-weekly/
 - Docker Hub: https://hub.docker.com/r/projectmonai/monailabel
+- Client API: https://www.youtube.com/watch?v=mPMYJyzSmyo
+- Demo Videos: https://www.youtube.com/c/ProjectMONAI

docs/source/installation.rst

@@ -21,7 +21,7 @@ and supported visualization tools with latest release of MONAI Label. Weekly pre
 
 Current Milestone Release of MONAI Label:
 
-* `0.4.2 <https://pypi.org/project/monailabel/>`_
+* `0.5.0 <https://pypi.org/project/monailabel/>`_
 
 MONAI Label Supported Stable Visualization Tools:
 

docs/source/modules.rst

@@ -101,7 +101,7 @@ discretization.
     def post_transforms(self, data=None):
         return [
             Activationsd(keys="pred", sigmoid=True),
-            AsDiscreted(keys="pred", threshold_values=True, logit_thresh=0.5),
+            AsDiscreted(keys="pred", threshold=0.5),
             ToNumpyd(keys="pred"),
         ]
 
@@ -142,7 +142,7 @@ in this example they follow the default behavior in the base class.
     def train_post_transforms(self, context: Context):
         return Compose([
             Activationsd(keys="pred", sigmoid=True),
-            AsDiscreted(keys="pred", threshold_values=True, logit_thresh=0.5),
+            AsDiscreted(keys="pred", threshold=0.5),
         ])
 
     def val_pre_transforms(self, context: Context):

docs/source/whatsnew.rst

@@ -15,6 +15,26 @@
 What's New
 ==========
 
+0.5.0
+=====
+- Endoscopy Sample App
+
+  - Tool Tracking segmentation model
+  - InBody vs OutBody (DeID) classification model
+  - DeepEdit interaction model for annotating tool
+  - CVAT Integration to support automated workflow to run Active Learning Iterations
+- Improving performance for Radiology App
+
+  - Support cache for pre-transforms in case repeated inference for interaction models
+  - Support cache for DICOM Web API responses
+  - Fix DICOM Proxy for wado/qido
+
+- Multi Stage `vertebra <https://github.com/Project-MONAI/MONAILabel/tree/main/sample-apps/radiology#multistage-vertebra-segmentation>`_ segmentation
+- Improvements for Epistemic based active learning strategy
+- Support for MONAI `1.0.0 <https://github.com/Project-MONAI/MONAI/releases/tag/1.0.0>`_
+
+
+
 0.4.2
 =====
 - MONAI Bundle App - Pull `compatible <https://github.com/Project-MONAI/MONAILabel/tree/main/sample-apps/monaibundle>`_ bundles from `MONAI Zoo <https://github.com/Project-MONAI/model-zoo>`_

monailabel/tasks/scoring/epistemic.py

@@ -18,13 +18,15 @@
 import torch
 from monai.inferers import sliding_window_inference
 from monai.transforms import Compose
+from monai.utils import deprecated
 
 from monailabel.interfaces.datastore import Datastore
 from monailabel.interfaces.tasks.scoring import ScoringMethod
 
 logger = logging.getLogger(__name__)
 
 
+@deprecated(since="0.5.0", msg_suffix="please use Epistemic v2 based strategy instead")
 class EpistemicScoring(ScoringMethod):
     """
     First version of Epistemic computation used as active learning strategy

monailabel/tasks/scoring/tta.py

@@ -39,6 +39,7 @@
 from monai.transforms.inverse_batch_transform import BatchInverseTransform
 from monai.transforms.transform import Randomizable
 from monai.transforms.utils import allow_missing_keys_mode
+from monai.utils import deprecated
 from monai.utils.enums import CommonKeys, InverseKeys
 from tqdm import tqdm
 
@@ -48,6 +49,7 @@
 logger = logging.getLogger(__name__)
 
 
+@deprecated(since="0.5.0", msg_suffix="please use Epistemic based strategy instead")
 class TTAScoring(ScoringMethod):
     """
     First version of test time augmentation active learning
@@ -236,7 +238,7 @@ class TestTimeAugmentation:
         .. code-block:: python
 
             transform = RandAffined(keys, ...)
-            post_trans = Compose([Activations(sigmoid=True), AsDiscrete(threshold_values=True)])
+            post_trans = Compose([Activations(sigmoid=True), AsDiscrete()])
 
             tt_aug = TestTimeAugmentation(
                 transform, batch_size=5, num_workers=0, inferrer_fn=lambda x: post_trans(model(x)), device=device

requirements.txt

@@ -10,7 +10,7 @@
 # limitations under the License.
 
 torch>=1.7
-monai[nibabel, skimage, pillow, tensorboard, gdown, ignite, torchvision, itk, tqdm, lmdb, psutil, openslide, fire]>=1.0.0rc3
+monai[nibabel, skimage, pillow, tensorboard, gdown, ignite, torchvision, itk, tqdm, lmdb, psutil, openslide, fire]>=1.0.0
 uvicorn==0.17.6
 pydantic==1.9.1
 python-dotenv==0.20.0